OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Tree Of Thoughts

An open-source Python implementation of the Tree of Thoughts reasoning approach for large language models, documented as part of the Swarms framework.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Tree Of Thoughts — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a task benefits from generating and comparing multiple partial solutions instead of relying on a single model response.

Who it is for

  • Python developers building LLM applications
  • AI engineers experimenting with prompt-based reasoning
  • Developers prototyping branching search and deliberate problem solving

Documented uses

  • Add multi-step reasoning to an LLM application
  • Explore several candidate reasoning paths
  • Evaluate and prune partial solutions
  • Retain the selected reasoning path and search metrics
Before you choose

Requirements & limits

The repository is public and licensed under Apache-2.0. The documented implementation uses Python 3.10+ and the Swarms package; model use requires a function-calling provider and an API key.

  • Whether the selected model supports function calling
  • Whether the task can define a useful thought description and evaluation criterion
  • Whether breadth-first search or depth-first search better fits the task
  • How candidate count, search depth and evaluation samples affect model-call volume
  • Whether retaining tree and usage data is useful for evaluation

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Swarms and configure TreeOfThoughts

Prepare the documented Python implementation for Tree of Thoughts use.

Before you start

  • Python 3.10 or later.
  • The swarms package.
  • A model that supports function calling through LiteLLM.
  • An API key stored in a .env file in the working directory.

Steps

  1. Install or upgrade Swarms with the command below.

    Documented command
    pip3 install -U swarms

  2. Create a .env file containing an appropriate provider API key, such as OPENAI_API_KEY, and set WORKSPACE_DIR as shown in the README.

  3. Import TreeOfThoughts from swarms and configure its model, search algorithm, depth, thought description, and evaluation criteria.

Expected outcome

The documented TreeOfThoughts component is configured and ready for a task.

Guide limitations

  • The model must support function calling.
  • The documentation does not establish compatibility for models beyond those supported by LiteLLM.
  • This recipe documents setup and configuration, not successful execution.
Documentation 1 ↗Documentation 2 ↗
Source-based practical guide

Run a TreeOfThoughts task and inspect its result

Execute the documented TreeOfThoughts quickstart and inspect the returned answer and search metadata.

Before you start

  • Swarms is installed and configured as documented.
  • A function-calling model and corresponding API key are available.
  • A configured TreeOfThoughts instance.

Steps

  1. Create a TreeOfThoughts instance with a model name, search algorithm, maximum depth, thought description, and evaluation criteria.

  2. Call agent.run(task) with the problem statement.

  3. Print the returned answer.

  4. Read agent.last_result to inspect the best reasoning steps, solved status, expanded nodes, model-call count, token usage, or the serialized tree.

Expected outcome

The task returns an answer, while `agent.last_result` exposes the documented search result and metadata.

Guide limitations

  • The README does not guarantee that every task will be solved.
  • Search cost grows with num_thoughts, breadth, max_depth, and n_evaluate_samples; max_expansions can bound expansion.
  • The model must support function calling.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
kyegomez/tree-of-thoughts · Official homepage title · retained in its source language
How we review sourcesSuggest a correction